Claude Sonnet 4.5

I've really got to refactor my side project which I tailored to just use OpenAI API calls. I think the Anthropic APIs are a bit different so I just never put in the energy to support the changes. I think I remember reading that there are tools to simpify this kind of work, to support multiple LLM APIs? I'm sure I could do it manually but how do you all support multiple API providers that have some differences in the API design?

Re: Claude Sonnet 4.5

#5

Post by yewenjie » Mon, Sep 29, 2025, 5:02 PM UTC

Looking at the chart here, it seems like Sonnet 4 was already better than GPT-5-codex in the SWE verified benchmark.

However, my subjective personal experience was GPT-5-codex was far better at complex problems than Claude Code.

Re: Claude Sonnet 4.5

#6

Post by willcodeforfoo » Mon, Sep 29, 2025, 5:03 PM UTC

cryptoz wrote: post #4

I've really got to refactor my side project which I tailored to just use OpenAI API calls. I think the Anthropic APIs are a bit different so I just never put in the energy to support the changes. I think I remember reading that there are tools to simpify this kind of work, to support multiple LLM APIs? I'm sure I could do it manually but how do you all support multiple API providers that have some differences in the…

https://openrouter.ai/?

Re: Claude Sonnet 4.5

#7

Post by SatvikBeri » Mon, Sep 29, 2025, 5:03 PM UTC

dbbk wrote: post #3

So Opus isn't recommended anymore? Bit confusing

For now, yeah. Presumably they'll come out with Opus 4.5 soon.

Re: Claude Sonnet 4.5

#8

Post by chipgap98 » Mon, Sep 29, 2025, 5:04 PM UTC

Interesting that this is better than Opus 4.1. I want to see how this holds up under real world use, but if that's the case its very impressive.

I wonder how long it will be before we get Opus 4.5

Re: Claude Sonnet 4.5

#9

Post by CuriouslyC » Mon, Sep 29, 2025, 5:05 PM UTC

yewenjie wrote: post #5

Looking at the chart here, it seems like Sonnet 4 was already better than GPT-5-codex in the SWE verified benchmark. However, my subjective personal experience was GPT-5-codex was far better at complex problems than Claude Code.

The Anthropic models have been vibe-coding tuned. They're beasts at simple python/ts programs, but they definitely fall apart with scientific/difficult code and large codebases. I don't expect that to change with the new Sonnet.

Re: Claude Sonnet 4.5

#10

Post by pinum » Mon, Sep 29, 2025, 5:07 PM UTC

cryptoz wrote: post #4

I've really got to refactor my side project which I tailored to just use OpenAI API calls. I think the Anthropic APIs are a bit different so I just never put in the energy to support the changes. I think I remember reading that there are tools to simpify this kind of work, to support multiple LLM APIs? I'm sure I could do it manually but how do you all support multiple API providers that have some differences in the…

I use LiteLLM as a proxy.